Cloud network fault detection method, device, equipment, storage medium and program product
By constructing a cloud network topology map, network data model, and network fault diagnosis rule map, and combining it with graph neural network training to generate a fault detection model, the problem of low efficiency in cloud network fault detection is solved, and efficient and accurate fault detection and root cause localization are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CLOUD TECH CO LTD
- Filing Date
- 2024-11-28
- Publication Date
- 2026-05-29
AI Technical Summary
Existing technologies for cloud network fault detection suffer from low efficiency and poor accuracy, are greatly influenced by the subjective opinions of technical personnel, and make it difficult to pinpoint the root cause of faults.
By constructing a cloud network topology map, network data model, and network fault diagnosis rule map, and training it with a graph neural network, a cloud network fault detection model is generated to achieve automated fault detection.
It improves the accuracy and efficiency of cloud network fault detection, reduces reliance on technical personnel, and enables rapid identification of the root cause of faults.
Smart Images
Figure CN119835147B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cloud computing technology, specifically to cloud network fault detection methods, devices, equipment, storage media, and program products. Background Technology
[0002] Cloud networks, based on cloud computing technology, integrate computing resources such as servers, storage devices, and databases, achieving efficient resource utilization through centralized management and scheduling. With the increasing prevalence of cloud networks, fault detection within them has become a pressing issue.
[0003] In related technologies, technical personnel with rich experience in problem handling and relevant professional knowledge can locate and diagnose faults in cloud networks. However, due to the high system complexity of cloud networks, there are many types of faults, the root cause of the fault is difficult to locate, and it is greatly affected by the subjective influence of technical personnel. Therefore, the threshold for fault detection is high, the accuracy is low, and the efficiency is low. Summary of the Invention
[0004] In view of this, the purpose of the present invention is to provide a cloud network fault detection method, apparatus, device, storage medium and program product to solve the problem of low efficiency in cloud network fault detection.
[0005] In a first aspect, the present invention provides a cloud network fault detection method, the method comprising:
[0006] Obtain the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and construct a cloud network topology map;
[0007] Obtain the characteristic parameters and operating status of each node in the target cloud network, and construct a network data model based on the cloud network topology map;
[0008] Obtain a cloud network fault detection knowledge base, and combine the cloud network topology map and the network data model to construct a network fault diagnosis rule map;
[0009] A graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, so as to perform cloud network fault detection.
[0010] In one optional implementation, each node in the target cloud network includes several network element nodes and several host nodes.
[0011] The process of acquiring the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and constructing a cloud network topology map, includes:
[0012] Obtain the topology, connectivity, and traffic flow between various network element nodes and host nodes in the target cloud network;
[0013] A cloud network topology graph is constructed using each network element node and each host node as entities, the topological relationships and connections between each network element node and each host node as entity attributes, and the traffic flow between each network element node and each host node as the edges between each entity.
[0014] In one optional implementation, the characteristic parameters of the node include the matching path and intermediate files for communication between the nodes, and the running status of the node includes the connection status, working status and traffic allocation of each node.
[0015] The process of acquiring the characteristic parameters and operating status of each node in the target cloud network, and constructing a network data model based on the cloud network topology map, includes:
[0016] Obtain the matching paths and intermediate files for communication between nodes in the target cloud network, as well as the connection status, working status, and traffic allocation of each node. Combine the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology map to construct a network data model.
[0017] In one optional implementation, the step of acquiring a cloud network fault detection knowledge base and constructing a network fault diagnosis rule graph by combining the cloud network topology map and the network data model includes:
[0018] Acquire cloud network expert experience, operation and maintenance documents, troubleshooting manuals, and historical fault records to build a cloud network fault detection knowledge base;
[0019] Based on the cloud network fault detection knowledge base, and combining the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology graph, as well as the characteristic parameters and operating status of each node in the network data model, a cloud network fault diagnosis rule graph is constructed with network fault problems as entities, the judgment conditions of network fault problems as entity attributes, and the association relationships between network fault problems as edges between entities.
[0020] In one optional implementation, a graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, including:
[0021] Using the cloud network topology graph, the network data model, and the network fault diagnosis rule graph as a dataset, a graph neural network is used to learn the weights of the edges between entities in the network fault diagnosis rule graph to obtain a cloud network fault detection model.
[0022] In one optional implementation, the cloud network fault detection includes:
[0023] The cloud network fault detection model is used to collect the characteristic parameters and operating status of each node in the network data model;
[0024] Based on the network fault diagnosis rule map and the characteristic parameters and operating status of each node in the network data model, cloud network faults are checked, located, and inferred, and the root causes of cloud network faults and their corresponding confidence probabilities are output.
[0025] Secondly, the present invention provides a cloud network fault detection device, the device comprising:
[0026] The topology graph module is used to obtain the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and to construct a cloud network topology graph.
[0027] The data model module is used to obtain the characteristic parameters and operating status of each node in the target cloud network, and to construct a network data model in combination with the cloud network topology map.
[0028] The rule graph module is used to acquire the cloud network fault detection knowledge base and, in combination with the cloud network topology graph and the network data model, construct a network fault diagnosis rule graph.
[0029] The fault detection module is used to train a cloud network fault detection model by employing a graph neural network based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, so as to perform cloud network fault detection.
[0030] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the cloud network fault detection method of the first aspect or any corresponding embodiment described above.
[0031] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the cloud network fault detection method of the first aspect or any corresponding embodiment described above.
[0032] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the cloud network fault detection method described in the first aspect or any corresponding embodiment thereof.
[0033] The technical solution provided by this invention may include the following beneficial effects:
[0034] The cloud network fault detection method provided by this invention first acquires the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network to construct a cloud network topology map. Next, it acquires the characteristic parameters and operating status of each node in the target cloud network, and combines this with the cloud network topology map to construct a network data model. Then, it acquires a cloud network fault detection knowledge base, and combines the cloud network topology map and the network data model to construct a network fault diagnosis rule graph. Finally, it employs a graph neural network to train the model based on the cloud network topology map, the network data model, and the network fault diagnosis rule graph to obtain a cloud network fault detection model for cloud network fault detection. This approach, by combining the cloud network topology map, the network data model, and the cloud network fault detection knowledge base, can construct a more targeted network fault diagnosis rule graph for the target cloud network, and train a more targeted cloud network fault detection model using these parameters. This eliminates the need for manual intervention and improves the accuracy and efficiency of subsequent cloud network fault detection. Attached Figure Description
[0035] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0036] Figure 1 This is a flowchart illustrating a cloud network fault detection method according to an embodiment of the present invention;
[0037] Figure 2 This is a flowchart illustrating another cloud network fault detection method according to an embodiment of the present invention;
[0038] Figure 3 This is a schematic diagram of cloud network fault detection according to an embodiment of the present invention;
[0039] Figure 4 This is a flowchart of cloud network fault detection according to an embodiment of the present invention;
[0040] Figure 5 This is a structural block diagram of a cloud network fault detection device according to an embodiment of the present invention;
[0041] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation
[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0043] This invention provides a cloud network fault detection method that improves the efficiency of cloud network fault detection by combining cloud network topology maps, network data models, and network fault diagnosis rule maps.
[0044] According to an embodiment of the present invention, a cloud network fault detection method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0045] This embodiment provides a cloud network fault detection method, which can be used for laptops, desktop computers, servers, etc. Figure 1 This is a flowchart of a cloud network fault detection method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:
[0046] Step S101: Obtain the topological relationships, connection relationships, and traffic flow of each node in the target cloud network, and construct a cloud network topology map.
[0047] The target cloud network is the cloud network to be fault-detected. Each node in the target cloud network represents a virtual or physical device. The topology of these nodes can be star, ring, bus, tree, mesh, etc. The connectivity between nodes refers to whether they are connected and the connection method, such as physical connections (e.g., network cables, fiber optics) or virtual connections (e.g., virtual network interfaces). Traffic flow refers to the direction of traffic transmission between nodes. This cloud network topology graph is constructed based on a knowledge graph, a structured knowledge representation method used to describe entities, concepts, and their relationships in the real world. A knowledge graph stores and organizes knowledge in the form of a graph, where nodes represent entities or concepts, and edges represent relationships between entities or concepts. Optionally, in this cloud network topology graph, each node of the target cloud network can be treated as an entity, connected based on topological and connectivity relationships, and the direction of the edges can be determined according to the traffic flow.
[0048] Step S102: Obtain the characteristic parameters and operating status of each node in the target cloud network, and construct a network data model based on the cloud network topology map.
[0049] The characteristic parameters of each node in the target cloud network can include the address assigned to the node, how it communicates with other nodes, etc. The operating status of each node can include how many other nodes it is currently connected to, whether it is in normal working condition, how much traffic it has been allocated, etc. The network metadata model is a structured data set used to describe and store the node characteristics, edge information, entity attributes, and graph structure of each node in the target cloud network. In this embodiment, the network metadata model can provide the topology, connection relationships, traffic flow, characteristic parameters, and operating status of each node in the target cloud network for subsequent cloud network fault detection.
[0050] Step S103: Obtain the cloud network fault detection knowledge base, and construct a network fault diagnosis rule map by combining the cloud network topology map and the network metadata model.
[0051] This cloud network fault detection knowledge base can be pre-built based on collected network data and historical fault information. The network fault diagnosis rule graph, constructed based on a knowledge graph, treats each fault as an entity and the relationships between faults as edges. This cloud network topology graph and the network metadata model provide the network fault diagnosis rule graph with various information about the target cloud network. This ensures that the network fault diagnosis rule graph contains not only content related to each fault but also information about the target cloud network, enabling more targeted network fault diagnosis and improving the accuracy of the diagnostic results.
[0052] Step S104: A graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map to perform cloud network fault detection.
[0053] Graph Neural Networks (GNNs) are deep learning models specifically designed for processing graph-structured data. They can capture the dependencies between nodes and the topology of the graph. By using information from the cloud network topology graph, the network metadata model, and the network fault diagnosis rule graph as a dataset, a GNN is trained to obtain a cloud network fault detection model. This model can predict the connections between various faults in the target cloud network, trace the root cause of the fault, and enable relevant technicians to perform repairs based on the identified root causes, thereby improving the efficiency of cloud network fault detection.
[0054] The cloud network fault detection method provided in this embodiment first acquires the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network to construct a cloud network topology map. Next, it acquires the characteristic parameters and operating status of each node in the target cloud network, and combines this with the cloud network topology map to construct a network data model. Then, it acquires a cloud network fault detection knowledge base, and combines the cloud network topology map and the network data model to construct a network fault diagnosis rule graph. Finally, it employs a graph neural network to train the model based on the cloud network topology map, the network data model, and the network fault diagnosis rule graph to obtain a cloud network fault detection model for cloud network fault detection. This scheme, by combining the cloud network topology map, the network data model, and the cloud network fault detection knowledge base, can construct a more targeted network fault diagnosis rule graph for the target cloud network, and train a more targeted cloud network fault detection model using these parameters. This eliminates the need for manual intervention and improves the accuracy and efficiency of subsequent cloud network fault detection.
[0055] This embodiment provides a cloud network fault detection method, which can be used for laptops, desktop computers, servers, etc. Figure 2 This is a flowchart of a cloud network fault detection method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:
[0056] Step S201: Obtain the topological relationships, connection relationships, and traffic flow of each node in the target cloud network, and construct a cloud network topology map.
[0057] Specifically, step S201 includes:
[0058] Step S2011: Obtain the topology, connection relationships, and traffic flow between each network element node and each host node in the target cloud network.
[0059] The target cloud network comprises several network element nodes and several host nodes. A network element refers to a network component, the basic unit constituting the target cloud network, responsible for handling tasks such as data transmission, routing, and switching. For example, a network element node can be a router, switch, load balancer, firewall, gateway, SDN (Software-Defined Networking) controller, etc., and can be a physical device or a virtual device. A host typically refers to a device that plays a leading role in the system, controlling and managing slave devices; the host itself is an independently operating computer system. For example, a host node can be a physical machine or a virtual machine, and can be a terminal device, client device, server device, etc.
[0060] Step S2012: Construct a cloud network topology graph with each network element node and each host node as entities, the topological relationship and connection relationship between each network element node and each host node as entity attributes, and the traffic flow between each network element node and each host node as the edges between each entity.
[0061] The weights of the edges between nodes are determined by the flow between the nodes.
[0062] Optionally, when at least one of the topological relationships, connectivity relationships, or traffic flows of each node in the target cloud network changes, the cloud network topology map is updated based on the changed topological relationships, connectivity relationships, and traffic flows of each node.
[0063] Step S202: Obtain the characteristic parameters and operating status of each node in the target cloud network, and construct a network data model by combining the cloud network topology map.
[0064] Optionally, the node's characteristic parameters include the matching paths and intermediate files for communication between nodes. The node's operational status includes the connection status, working status, and traffic allocation of each node. The intermediate files can be routing tables or forwarding tables between physical machines, flow tables between virtual machines, or intermediate files for communication between the cloud and on-premises environments. The node's characteristic parameters may also include IP address, subnet mask, default gateway, server address, MAC address, bandwidth utilization, packet loss rate, and latency. The node's connection status can include the number of established connections and connection stability; its working status can be "up," "unavailable," or "down"; and its traffic allocation can include the inbound data volume, outbound data volume, and data transmission rate flowing through the node.
[0065] Specifically, the matching paths and intermediate files for communication between nodes in the target cloud network are obtained, as well as the connection status, working status, and traffic distribution of each node. Combined with the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology map, a network data model is constructed.
[0066] Optionally, when the characteristic parameters and operating status of each node in the cloud network topology map and / or the target cloud network change, the network data model is updated based on the changed cloud network topology map and / or the characteristic parameters and operating status of each node in the target cloud network.
[0067] Step S203: Obtain the cloud network fault detection knowledge base, and construct a network fault diagnosis rule map by combining the cloud network topology map and the network metadata model.
[0068] Specifically, step S203 includes:
[0069] Step S2031: Obtain cloud network expert experience, operation and maintenance documents, troubleshooting manuals, and historical fault records to build a cloud network fault detection knowledge base.
[0070] The experience of cloud network experts, operation and maintenance documents, troubleshooting manuals, and historical fault records contain various network fault events, network fault objects, and the relationships between these events and objects. By performing semantic recognition on these materials, a cloud network fault detection knowledge base can be constructed.
[0071] Step S2032: Based on the cloud network fault detection knowledge base, and combining the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology graph and the characteristic parameters and operating status of each node in the network metadata model, a cloud network fault diagnosis rule graph is constructed, with network fault problems as entities, the judgment conditions of network fault problems as entity attributes, and the association relationships between network fault problems as edges between entities.
[0072] The cloud network topology map and network data model provide relevant information about the target cloud network, which is then labeled and mapped to the cloud network fault detection process. Data from the cloud network fault detection knowledge base is accessed through corresponding interfaces, and entity recognition and relationship extraction are performed on this knowledge base to construct a cloud network fault diagnosis rule graph. Network fault problems include network fault events and network fault objects. The judgment conditions for network fault problems can be judgment rules, judgment parameters, judgment states, etc., such as a parameter of 0 indicating a fault or an offline state indicating a fault. Edges between two entities represent the association between them, and the weight of the edge indicates the degree of association. The triples in the cloud network fault diagnosis rule graph indicate the logical relationships and degree of association between the network fault problems corresponding to each entity.
[0073] Optionally, when the cloud network fault detection knowledge base, cloud network topology map, and network data model change, the cloud network fault diagnosis rule map is updated based on the changed cloud network fault detection knowledge base, cloud network topology map, and network data model.
[0074] Step S204: A graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map to perform cloud network fault detection.
[0075] The entities in this network fault diagnosis rule graph represent different types of network fault problems, while the nodes in the cloud network topology graph represent network elements or hosts. By constructing an association matrix between network fault problems and root causes, relevant information of the target cloud network in the cloud network topology graph can be linked with the network fault problems and root causes in the network fault diagnosis rule graph, enabling reasoning from network fault problems in the target cloud network to their root causes. The characteristic parameters and operating states of nodes in the target cloud network in the network data model can provide the graph neural network with information such as node features, edge information, entity attributes, graph structure, and adjacency matrix, allowing the graph neural network to learn the embedded representation of nodes, capture complex relationships between nodes, and realize cloud network fault detection. A multi-task learning framework can also be used to simultaneously process the cloud network topology graph, the network data model, and the network fault diagnosis rule graph. During graph neural network training, features from these three graphs are shared, optimizing the graph neural network parameters, improving the accuracy of the obtained cloud network fault detection model, and consequently improving the accuracy of subsequent cloud network fault detection using this model.
[0076] Specifically, the cloud network topology graph, the network metadata model, and the network fault diagnosis rule graph are used as datasets. Graph neural networks are then used to learn the weights of the edges between entities in the network fault diagnosis rule graph to obtain the cloud network fault detection model.
[0077] Once the cloud network fault detection model is obtained, it can be used to perform fault detection (online inference) on the target cloud network. The detection time interval can be set, such as once a day, and fault detection can also be actively triggered through corresponding commands or functions. During fault detection, the cloud network fault detection model is first used to collect the characteristic parameters and operating status of each node in the network data model. Then, based on the network fault diagnosis rule graph and the characteristic parameters and operating status of each node in the network data model, cloud network fault checks are performed. If a fault is detected in the target cloud network, the fault is located and inferred, outputting the root cause of the cloud network fault and its corresponding confidence probability. Multiple root causes and their corresponding confidence probabilities can be output at once for reference by relevant technical personnel to promptly repair the target cloud network. Relevant technical personnel can also fine-tune and update the cloud network fault detection model as needed, for example, updating it when new improvements are discovered during fault detection.
[0078] The cloud network fault detection method provided in this embodiment first acquires the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network to construct a cloud network topology map. Next, it acquires the characteristic parameters and operating status of each node in the target cloud network, and combines this with the cloud network topology map to construct a network data model. Then, it acquires a cloud network fault detection knowledge base, and combines the cloud network topology map and the network data model to construct a network fault diagnosis rule graph. Finally, it employs a graph neural network to train the model based on the cloud network topology map, the network data model, and the network fault diagnosis rule graph to obtain a cloud network fault detection model for cloud network fault detection. This scheme, by combining the cloud network topology map, the network data model, and the cloud network fault detection knowledge base, can construct a more targeted network fault diagnosis rule graph for the target cloud network, and train a more targeted cloud network fault detection model using these parameters. This eliminates the need for manual intervention and improves the accuracy and efficiency of subsequent cloud network fault detection.
[0079] As one or more specific application embodiments of the present invention, the optimal implementation scheme or the scheme that the inventors most want to embody is described below in conjunction with specific application scenarios.
[0080] Figure 3 This is a schematic diagram of cloud network fault detection according to an embodiment of the present invention. Figure 4 This is a flowchart of cloud network fault detection according to an embodiment of the present invention. Figure 3 As shown, data is first collected to construct a network topology map and network data model. Then, the network topology map and network data model are integrated into the construction of a network problem diagnosis knowledge base to perform entity recognition and relationship extraction, thereby constructing a network problem diagnosis rule graph. For example... Figure 4 As shown, data collection and knowledge extraction are performed first, followed by entity recognition and relationship extraction to construct a network topology graph and a network problem diagnosis rule graph. Then, a graph neural network is trained, and online reasoning is performed through the trained graph neural network (i.e., the cloud network fault detection model), and the knowledge base is updated in a timely manner.
[0081] This embodiment also provides a cloud network fault detection device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0082] This embodiment provides a cloud network fault detection device, such as... Figure 5 As shown, it includes:
[0083] The topology graph module 501 is used to obtain the topological relationships, connection relationships and traffic flow of each node in the target cloud network and construct a cloud network topology graph.
[0084] Data model module 502 is used to obtain the characteristic parameters and operating status of each node in the target cloud network, and to construct a network data model by combining the cloud network topology map.
[0085] The rule graph module 503 is used to acquire the cloud network fault detection knowledge base, and combine the cloud network topology graph and the network data model to construct a network fault diagnosis rule graph.
[0086] The fault detection module 504 is used to train a cloud network fault detection model by employing a graph neural network based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, so as to perform cloud network fault detection.
[0087] In one optional implementation, each node in the target cloud network includes several network element nodes and several host nodes; the topology graph module is also used to: obtain the topological relationships, connection relationships and traffic flow between each network element node and each host node in the target cloud network; construct a cloud network topology graph with each network element node and each host node as entities, the topological relationships and connection relationships between each network element node and each host node as entity attributes, and the traffic flow between each network element node and each host node as the edges between each entity.
[0088] In one optional implementation, the node's characteristic parameters include the matching path and intermediate files for communication between nodes, and the node's operating status includes the connection status, working status, and traffic allocation of each node. The data model module is also used to: obtain the matching path and intermediate files for communication between nodes in the target cloud network, as well as the connection status, working status, and traffic allocation of each node, and construct a network data model by combining the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology map.
[0089] In one optional implementation, the rule graph module is further used to: acquire cloud network expert experience, operation and maintenance documents, troubleshooting manuals, and historical fault records to build a cloud network fault detection knowledge base; based on the cloud network fault detection knowledge base, combined with the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology graph and the characteristic parameters and operating status of each node in the network metadata model, a cloud network fault diagnosis rule graph is constructed, with network fault problems as entities, judgment conditions of network fault problems as entity attributes, and the association relationships between network fault problems as edges between entities.
[0090] In one optional implementation, the fault detection module is further configured to: use the cloud network topology graph, the network data model, and the network fault diagnosis rule graph as a dataset, and use a graph neural network to learn the weights of the edges between each entity in the network fault diagnosis rule graph to obtain a cloud network fault detection model.
[0091] In an optional implementation, the fault detection module is further configured to: use the cloud network fault detection model to collect the characteristic parameters and operating status of each node in the network data model; based on the network fault diagnosis rule map and the characteristic parameters and operating status of each node in the network data model, perform cloud network fault inspection, location and inference, and output the root cause of the cloud network fault and the corresponding confidence probability.
[0092] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0093] In this embodiment, the cloud network fault detection device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0094] This invention also provides a computer device having the above-described features. Figure 5 The cloud network fault detection device shown.
[0095] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.
[0096] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0097] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.
[0098] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0099] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0100] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.
[0101] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.
[0102] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0103] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0104] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and all such modifications and variations fall within the protection scope of the present invention.
Claims
1. A cloud network fault detection method, characterized in that, The method includes: Obtain the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and construct a cloud network topology map; Obtain the characteristic parameters and operating status of each node in the target cloud network, and construct a network data model based on the cloud network topology map; A cloud network fault detection knowledge base is acquired, and a network fault diagnosis rule graph is constructed by combining the cloud network topology map and the network data model. Specifically, relevant information about the target cloud network provided by the cloud network topology map and the network data model is mapped to the cloud network fault detection process using tags. Data from the cloud network fault detection knowledge base is then called through corresponding interfaces to perform entity recognition and relationship extraction on the data in the knowledge base, thereby constructing the cloud network fault diagnosis rule graph. A graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, so as to perform cloud network fault detection.
2. The method according to claim 1, characterized in that, Each node in the target cloud network includes several network element nodes and several host nodes. The process of acquiring the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and constructing a cloud network topology map, includes: Obtain the topology, connectivity, and traffic flow between various network element nodes and host nodes in the target cloud network; A cloud network topology graph is constructed using each network element node and each host node as entities, the topological relationships and connections between each network element node and each host node as entity attributes, and the traffic flow between each network element node and each host node as the edges between each entity.
3. The method according to claim 2, characterized in that, The characteristic parameters of the nodes include the matching paths and intermediate files for communication between the nodes, and the running status of the nodes includes the connection status, working status and traffic allocation of each node. The process of acquiring the characteristic parameters and operating status of each node in the target cloud network, and constructing a network data model based on the cloud network topology map, includes: Obtain the matching paths and intermediate files for communication between nodes in the target cloud network, as well as the connection status, working status, and traffic allocation of each node. Combine the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology map to construct a network data model.
4. The method according to claim 3, characterized in that, The process of acquiring a cloud network fault detection knowledge base, combining the cloud network topology map and the network data model, and constructing a network fault diagnosis rule map includes: Acquire cloud network expert experience, operation and maintenance documents, troubleshooting manuals, and historical fault records to build a cloud network fault detection knowledge base; Based on the cloud network fault detection knowledge base, and combining the topological relationships, connection relationships, and traffic flow of each node in the cloud network topology graph with the characteristic parameters and operating status of each node in the network data model, a cloud network fault diagnosis rule graph is constructed with network fault problems as entities, the judgment conditions of network fault problems as entity attributes, and the association relationships between network fault problems as edges between entities.
5. The method according to any one of claims 1 to 4, characterized in that, A graph neural network is used to train a cloud network fault detection model based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, including: Using the cloud network topology graph, the network data model, and the network fault diagnosis rule graph as a dataset, a graph neural network is used to learn the weights of the edges between entities in the network fault diagnosis rule graph to obtain a cloud network fault detection model.
6. The method according to claim 5, characterized in that, The cloud network fault detection includes: The cloud network fault detection model is used to collect the characteristic parameters and operating status of each node in the network data model; Based on the network fault diagnosis rule map and the characteristic parameters and operating status of each node in the network data model, cloud network faults are checked, located, and inferred, and the root causes of cloud network faults and their corresponding confidence probabilities are output.
7. A cloud network fault detection device, characterized in that, The device includes: The topology graph module is used to obtain the topological relationships, connectivity relationships, and traffic flow of each node in the target cloud network, and to construct a cloud network topology graph. The data model module is used to obtain the characteristic parameters and operating status of each node in the target cloud network, and to construct a network data model in combination with the cloud network topology map. The rule graph module is used to acquire a cloud network fault detection knowledge base, and combine the cloud network topology graph and the network data model to construct a network fault diagnosis rule graph. Specifically, relevant information about the target cloud network provided by the cloud network topology graph and the network data model is mapped to the cloud network fault detection process through tags, and data in the cloud network fault detection knowledge base is called through corresponding interfaces to perform entity recognition and relationship extraction on the data in the cloud network fault detection knowledge base, thereby constructing the cloud network fault diagnosis rule graph. The fault detection module is used to train a cloud network fault detection model by employing a graph neural network based on the cloud network topology map, the network data model, and the network fault diagnosis rule map, so as to perform cloud network fault detection.
8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the cloud network fault detection method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the cloud network fault detection method according to any one of claims 1 to 6.
10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the cloud network fault detection method according to any one of claims 1 to 6.